The Software Agents Mailing List FAQ
This file contains the Frequently Asked Questions list for the software agents mailing list. Please note that this FAQ will be updated (semi-)regularly and is sure to be incomplete in areas.
Table of Contents
This mailing list is devoted to the issues of Software Agents. The term `agent' is ill-defined but discussion focuses on software agents as opposed to hardware (robots) or human agents.
The purpose of the list is to provide a forum for the discussion of issues related to software agents. The study of software agents is an emerging field combining elements of traditional artificial intelligence, game theory, psychology, and object-oriented programming (among other fields).
To join the list, send email to firstname.lastname@example.org with "subscribe agents <your name here>" in the body of the message.
To have yourself removed from the mailing list send a message to email@example.com (from the account with which you originally subscribed) with "unsubscribe agents" in the body of the message.
Further instructions will be automatically mailed to you.
The list maintainer is Raymond Johnson.
An archive of the list exists on the WWW at URL:
First of all, it should be noted that there are widely varying definitions of the term `agent'. This FAQ will not attempt to provide an authoritative definition, but will mention some qualities shared by most agents, and will provide pointers to further sources of information.
Agent-oriented programming (AOP) (a term coined by researcher Yoav Shoham) concerns itself with the creation of software agents. A dictionary definition of the term `agent' follows:
"An entity authorized to act on another's behalf."
A software agent is a piece of software which acts to accomplish tasks on behalf of its user.
Many agents are based on the idea that the user need only specify specify a high-level goal instead of issuing explicit instructions, leaving the `how' and `when' decisions to the agent.
This list of qualities of software agents is taken from a paper by O. Etzioni and Dan Weld, appearing in IEEE Expert, July 1995.
an agent is able to take initiative and exercise a non-trivial degree of control over its own actions
an agent accepts high-level requests indicating what a human wants and is responsible for deciding how and where to satisfy the request.
an agent does not blindly obey commands, but has the ability to modify requests, ask clarification questions, or even refuse to satisfy certain requests.
the agent's actions are not scripted; it is able to dynamically choose which actions to invoke, and in what sequence, in response to the state of its external environment.
unlike standard programs which are directly invoked by the user, an agent can sense changes to its environment and decide when to act.
- Temporal continuity
agents are continuously running processes, not ``one-shot'' computations that map a single input to a single output, then terminate.
an agent has a well-defined, believable "personality" and emotional state.
the agent is able to engage in complex communication with other agents, including people, in order to obtain information or enlist their help in accomplishing its goals.
the agent automatically customizes itself to the preferences of its user based on previous experience. The agent also automatically adapts to changes in its environment.
an agent is able to transport itself from one machine to another and across different system architectures and platforms.
- The Java Agent Template by Robert Frost at Stanford University
... Version 2.0 provides basic agent functionality packaged as a Java(tm) application. This agent can be executed as a stand alone application or as an applet via a WWW browser. Provides for asynchronous exchange of KQML messages via sockets.
- Tcl 7.5 from the labs of Sun Microsystems, incorporating many of the features of safe-Tcl.
Agent Tcl is a mobile agent system that is roughly similar to Telescript (except that it uses Tcl, is lightweight, and currently has limited security).
- TACOMA from the University of Tromsų and Cornell University.
- Clearlake agent technology from Guideware Corporation
MOUNTAIN VIEW, CA, October 24, 1995 -- Guideware Corporation today announced Clearlake, a suite of products for programming, deploying and tracking mobile software agents. Mobile software agents can be programmed to navigate LANs, WANs or the Internet to perform complex processes involving multiple people and applications on Windows, Unix or Macintosh.
- Open Sesame
Charles River Analytics is a Macintosh and Windows software developer located in Cambridge, MA. We designed Open Sesame!, the first intelligent agent for the Macintosh, and Smarts by Open Sesame!, the intelligence engine that allows third party vendors to add intelligence to their applications.
- Agent-Related Conferences, Workshops, Seminars, Funding opportunities, etc.
Conferences, workshops, seminars and other events which are relevant to intelligent software agents and KQML.
- Conference list maintained by Wolfram Willuhn
- First International Conference on Autonomous Agents
February 5-8, 1997; Mariott Hotel, Marina del Rey, California
This conference will bring together researchers interested in modeling and building autonomous agents. Agents are computational systems that inhabit dynamic, unpredictable environments. They interpret sensor data that reflect events in the environment and execute motor commands that produce effects in the environment. An agent is "autonomous" to the degree that it decides for itself how to relate sensor data to motor commands in its efforts to achieve goals, satisfy motivations, etc.
- PAAM96 - The First International Conference and Exhibition on The Practical Application of Intelligent Agents and Multi-Agent Technology
Monday 22nd April - Wednesday 24th April 1996, London, UK
The Commercial Value of Agents:- An Exploration Through Practical Applications
PAAM96 - The First International Conference and Exhibition on the Practical Application of Intelligent Agents and MultiAgents is a totally new conference which aims to demonstrate the use of agent technology for solving real-world problems in business, industry, and commerce.
The Third International Workshop on AGENT THEORIES, ARCHITECTURES, AND LANGUAGES (ATAL-96)
To be held at ECAI-96, Budapest, Hungary, August 12--13, 1996
The emergence of intelligent agent technology is one of the most exciting and important events to occur in computer science during the 1990s. It is now widely accepted that this technology will play a central role in the development of complex distributed systems, networked information systems, and computer interfaces during the twenty-first century. The aim of this workshop is to bring together researchers interested in the agent-level, micro aspects of this emerging technology.
- The Intelligent Information Agents Workshops (1994, and 1995)
This document is maintained by Marc Belgrave and has been retrieved times.
Served fresh since Sunday, 09-Feb-97 05:37:10 EST
[ Design by F.i.v.e F.o.o.t S.e.v.e.n Web Productions ]